Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Christopher D. Manning

Christopher D. Manning

21 paper cards in Mova's library · 2003–2021

Christopher D. Manning wrote 21 of the papers Mova reads, in 2003–2021, most of them on Universal Dependencies, Dependency parsing, Treebanks; often with Marie-Catherine de Marneffe, Joakim Nivre, Sebastian Schuster.

OpenAlex · ORCID · h-index 140 · 185462 citations · 781 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Universal Dependencies 6 · Dependency parsing 4 · Treebanks 4 · Part-of-speech tagging 3

Papers

  1. Universal Dependencies (2021)
    This article sets out the linguistic theory behind Universal Dependencies (UD), which is at once a cross-linguistically consistent morphosyntactic annotation scheme, an open research community and a growing collection of treebanks.
  2. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020)
    Stanza is a Python toolkit whose pipeline is neural from raw text to dependencies, for 66 languages. It has a combined tokenizer and sentence splitter, multi-word-token expansion (a frequency lexicon with a sequence-to-sequence model), a POS and feature tagger that conditions XPOS and features on UPOS, a lemmatizer…
  3. Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection (2020)
    The paper describes the UD v2 guidelines and the state of the collection at release 2.5: 157 treebanks in 90 languages, built by more than 300 contributors.
  4. Sentences with Gapping: Parsing and Reconstructing Elided Predicates (2018)
    In "Paul likes coffee and Mary tea" the verb is elided, so standard parsers attach the remnants badly and downstream relation extraction misses the predicate.
  5. CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (2017)
    The shared task asks systems to parse raw text, with no gold tokenization, sentence splitting or tags, into UD trees for 49 languages.
  6. Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task (2017)
    The Stanford system is a biaffine graph parser: a BiLSTM encoder, separate ReLU layers for the head and dependent roles of arcs and labels, and biaffine scorers for arcs and labels.
  7. Arc-swift: A Novel Transition System for Dependency Parsing (2017)
    Transition-based parsers reach a distant attachment only through a sequence of local shifts and reduces, and every step is a place to make an error.
  8. Gapping Constructions in Universal Dependencies v2 (2017)
    This is a design paper rather than an experiment. It asks how gapping (the omission of a repeated verb, as in "John likes tea, and Mary coffee") should be represented in UD v2. The authors survey the cross-linguistic patterns of gapping, including languages where the overt verb sits in the last conjunct, and compare…
  9. Deep Biaffine Attention for Neural Dependency Parsing (2016)
    The paper builds on the neural graph-based parser of Kiperwasser and Goldberg. It uses a larger and more heavily regularised BiLSTM encoder, passes the top recurrent states through dimension-reducing MLPs, and replaces the MLP attention and the affine label classifier with biaffine ones: one for arc scores over all…
  10. Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks (2016)
    Shallow understanding tasks such as relation extraction need direct links between content words, which a strict basic tree lacks: in "Fred started to laugh" the controlled verb has no subject edge.
  11. Universal Dependencies v1: A Multilingual Treebank Collection (2016)
    The paper is the reference for the first UD release. It sets out the design principles: dependency-based and lexicalist annotation, the recoverability principle (every syntactic word must map back to the raw text), content words as the backbone of the tree with function words as dependents, and a closed inventory of…
  12. Universal Stanford dependencies: A cross-linguistic typology (2014)
    The paper reconstructs the typology behind Stanford Dependencies and proposes a two-layer taxonomy: 42 universal grammatical relations that are broadly attested across languages, with language-specific subtypes added under them.
  13. More Constructions, More Genres: Extending Stanford Dependencies (2013)
    The Stanford scheme was built on newswire and gives little analysis to constructions that are rare there but common in web text: tough adjectives, free relatives, comparatives, small clauses, questions, imperatives, fragments and lists.
  14. Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics? (2011)
    Taggers report about 97% token accuracy, but only about 56% of sentences are fully right, and a single error can break a downstream parser.
  15. Better Arabic Parsing: Baselines, Evaluations, and Analysis (2010)
    Green and Manning ask why constituency parsers for Modern Standard Arabic lag behind English results on the Penn Arabic Treebank (ATB).
  16. Was It Good? It Was Provocative.'' Learning the Meaning of Scalar Adjectives (2010)
    Indirect answers to yes/no questions often do not say "yes" or "no" outright. "Was it good? It was provocative" leaves the answer open, while "It was great" does not. The authors mine two kinds of evidence. First, scale order between gradable adjectives comes from online IMDB reviews: a word's expected star rating…
  17. Multi-word expressions in textual inference: Much ado about nothing? (2009)
    The paper asks whether multi-word expressions (MWEs) matter for recognising textual entailment (RTE). It uses the manual Microsoft Research word alignments for the RTE2 data and counts the MWEs that appear as multi-word alignment links. Only 81 (dev) and 60 (test) true MWEs occur, in 8.2% of the 1,600 sentence pairs…
  18. The Stanford Typed Dependencies Representation (2008)
    The paper describes Stanford typed dependencies (SD), a dependency scheme designed to make parser output usable by people outside linguistics who need to extract relations from text.
  19. Generating Typed Dependency Parses from Phrase Structure Parses (2006)
    The paper describes a rule system that turns Penn Treebank phrase-structure trees, as produced by the Stanford parser, into typed dependencies.
  20. LinGO Redwoods: A Rich and Dynamic Treebank for HPSG (2004)
    Not read: this card is written from what is reliably known about the paper, and every idea is marked to check against the text.
  21. Accurate Unlexicalized Parsing (2003)
    The paper asks how far a PCFG with no lexical items can go on the Penn Treebank. A vanilla treebank grammar parses badly because its independence assumptions are too strong. Adding simple linguistic state splits, such as parent annotation, marking of base noun phrases, tag splits for function words and horizontal…

Co-authors (82)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/christopher-d-manning/